{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OSAQPBI6OK7GIN2XTKUCBEESUI","short_pith_number":"pith:OSAQPBI6","schema_version":"1.0","canonical_sha256":"748107851e72be6437579aa8209092a21f9d15a1d07a1860ed2eaad77c372923","source":{"kind":"arxiv","id":"2311.18760","version":4},"attestation_state":"computed","paper":{"title":"TaskBench: Benchmarking Large Language Models for Task Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongsheng Li, Kaitao Song, Kan Ren, Siyu Yuan, Weiming Lu, Wenqi Zhang, Xu Tan, Yongliang Shen, Yueting Zhuang","submitted_at":"2023-11-30T18:02:44Z","abstract_excerpt":"In recent years, the remarkable progress of large language models (LLMs) has sparked interest in task automation, which involves decomposing complex tasks described by user instructions into sub-tasks and invoking external tools to execute them, playing a central role in autonomous agents. However, there is a lack of systematic and standardized benchmarks to promote the development of LLMs in task automation. To address this, we introduce TaskBench, a comprehensive framework to evaluate the capability of LLMs in task automation. Specifically, task automation can be divided into three critical "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2311.18760","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-30T18:02:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"286a6e8fac6874174a0790aafc029380ddb31e45a88da4363a225aff9d63e070","abstract_canon_sha256":"6c53eec99c54230a8983da974f32025c5828cf8cc3c14dca3c34f901f2a4d9c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:24.916962Z","signature_b64":"pw5KQ2xm/MeS3njw7Gdp/b2qVO7vjRs7rDzMYp/7b2bv3osJA5shJj+rr1bwFN0zafb0maUG0paMvycX0VpsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"748107851e72be6437579aa8209092a21f9d15a1d07a1860ed2eaad77c372923","last_reissued_at":"2026-07-05T09:29:24.916468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:24.916468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TaskBench: Benchmarking Large Language Models for Task Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongsheng Li, Kaitao Song, Kan Ren, Siyu Yuan, Weiming Lu, Wenqi Zhang, Xu Tan, Yongliang Shen, Yueting Zhuang","submitted_at":"2023-11-30T18:02:44Z","abstract_excerpt":"In recent years, the remarkable progress of large language models (LLMs) has sparked interest in task automation, which involves decomposing complex tasks described by user instructions into sub-tasks and invoking external tools to execute them, playing a central role in autonomous agents. However, there is a lack of systematic and standardized benchmarks to promote the development of LLMs in task automation. To address this, we introduce TaskBench, a comprehensive framework to evaluate the capability of LLMs in task automation. Specifically, task automation can be divided into three critical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18760","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.18760/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.18760","created_at":"2026-07-05T09:29:24.916533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18760v4","created_at":"2026-07-05T09:29:24.916533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18760","created_at":"2026-07-05T09:29:24.916533+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSAQPBI6OK7G","created_at":"2026-07-05T09:29:24.916533+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSAQPBI6OK7GIN2X","created_at":"2026-07-05T09:29:24.916533+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSAQPBI6","created_at":"2026-07-05T09:29:24.916533+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18051","citing_title":"Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11830","citing_title":"Skill-Augmented AI Agents for Medical Research Analysis: An Exploratory Multi-Model Human Evaluation in an NSCLC Transcriptomic Biomarker Task","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31392","citing_title":"ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25310","citing_title":"Tool-Call Dependency Structure is Linearly Decodable in LLM Agent Residual Streams","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21265","citing_title":"ToolMATH: A Diagnostic Benchmark for Long-Horizon Tool Use under Systematic Tool-Catalog Constraints","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":133,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16508","citing_title":"The Scaling Laws of Skills in LLM Agent Systems","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16902","citing_title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03986","citing_title":"From Intent to Execution: Composing Agentic Workflows with Agent Recommendation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":131,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI","json":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI.json","graph_json":"https://pith.science/api/pith-number/OSAQPBI6OK7GIN2XTKUCBEESUI/graph.json","events_json":"https://pith.science/api/pith-number/OSAQPBI6OK7GIN2XTKUCBEESUI/events.json","paper":"https://pith.science/paper/OSAQPBI6"},"agent_actions":{"view_html":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI","download_json":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI.json","view_paper":"https://pith.science/paper/OSAQPBI6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18760&json=true","fetch_graph":"https://pith.science/api/pith-number/OSAQPBI6OK7GIN2XTKUCBEESUI/graph.json","fetch_events":"https://pith.science/api/pith-number/OSAQPBI6OK7GIN2XTKUCBEESUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI/action/storage_attestation","attest_author":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI/action/author_attestation","sign_citation":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI/action/citation_signature","submit_replication":"https://pith.science/pith/OSAQPBI6OK7GIN2XTKUCBEESUI/action/replication_record"}},"created_at":"2026-07-05T09:29:24.916533+00:00","updated_at":"2026-07-05T09:29:24.916533+00:00"}